IOS Mobile App Analysis

IOS Mobile App Analysis

Team 4 B for BA780

Team members: Yuhong Lu, Xiaohan Mei, Ziyan Pei, Peng Yuan, Mengqing Zhang, Jiayuan Zou

library(tidyverse)

Registered S3 method overwritten by 'dplyr':
  method           from
  print.rowwise_df     
-- Attaching packages --------------------------------------- tidyverse 1.2.1 --
v ggplot2 3.2.1     v purrr   0.3.2
v tibble  2.1.3     v dplyr   0.8.3
v tidyr   0.8.3     v stringr 1.4.0
v readr   1.3.1     v forcats 0.4.0
-- Conflicts ------------------------------------------ tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(readr)
library(magrittr)

Attaching package: 㤼㸱magrittr㤼㸲

The following object is masked from 㤼㸱package:purrr㤼㸲:

    set_names

The following object is masked from 㤼㸱package:tidyr㤼㸲:

    extract

library(ggplot2)

Data Cleaning & Merge

AppleStore <- read_csv("AppleStore.csv")

Missing column names filled in: 'X1' [1]Parsed with column specification:
cols(
  X1 = col_double(),
  id = col_double(),
  track_name = col_character(),
  size_bytes = col_double(),
  currency = col_character(),
  price = col_double(),
  rating_count_tot = col_double(),
  rating_count_ver = col_double(),
  user_rating = col_double(),
  user_rating_ver = col_double(),
  ver = col_character(),
  cont_rating = col_character(),
  prime_genre = col_character(),
  sup_devices.num = col_double(),
  ipadSc_urls.num = col_double(),
  lang.num = col_double(),
  vpp_lic = col_double()
)

descript <- read_csv("appleStore_description.csv")

Parsed with column specification:
cols(
  id = col_double(),
  track_name = col_character(),
  size_bytes = col_double(),
  app_desc = col_character()
)

AppleStore

descript

# Apple Store
AppleStore$currency <- as.factor(AppleStore$currency)
# Get primary key - ID
AppleStore %>% select(id) %>% group_by(id) %>% summarize(count=n()) %>% filter(count>1)

AppleStore %>% select(track_name) %>% group_by(track_name) %>% summarize(count=n()) %>% filter(count>1)

descript %>% select(id) %>% group_by(id) %>% summarize(count=n()) %>% filter(count>1)

descript %>% select(track_name) %>% group_by(track_name) %>% summarize(count=n()) %>% filter(count>1)

# the primary key is ID
# Merge two dataset
AppleStore %>% merge(descript, by='id') %>% 
  select(everything(),-X1,-size_bytes.x,-track_name.y) %>% rename(size_byte=size_bytes.y) ->AP
AP_omit <- na.omit(AP)
any(is.na(AP_omit))

[1] FALSE

write.csv(AP_omit,'AP_omit.csv')
AP_omit

NA